An open source alternative to some of Slack AI's premium features
The official Slack AI product looks great, but with limited access and add-on pricing, I decided to open-source the version I built. Especially for all the communities on Slack that would have to convert to paid and buy the upgrade to access the official SlackAI product/add-on which is not going to be financially viable in most cases. There's no plan to sell anything, just something I built as a way to learn some new tools that I thought others might get use out of. The repo is a ready-to-run slack app that provides thread summaries and channel overviews on demand using OpenAI (heavy…
In plain words
This open-source Slack app generates thread summaries and channel overviews on demand, offering functionality similar to Slack's premium AI features at no cost. Built by a developer to avoid paid upgrades for communities, it uses OpenAI's language models with standard NLP analysis. The ready-to-run application is designed for technical users who want AI-powered Slack insights without subscription fees, and supports integration with alternative models like Claude or Ollama.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
The official Slack AI product looks great, but with limited access and add-on pricing, I decided to open-source the version I built. Especially for all the communities on Slack that would have to convert to paid and buy the upgrade to access the official SlackAI product/add-on which is not going to be financially viable in most cases. There's no plan to sell anything, just something I built as a way to learn some new tools that I thought others might get use out of. The repo is a ready-to-run slack app that provides thread summaries and channel overviews on demand using OpenAI (heavy lifting done by gpt-3.5-turbo and a touch of gpt-4) and some standard NLP analysis. Anyone technical could easily swap in Claude or Ollama (and i'd welcome the pull request, it's been on my to do list!). There's a link in the readme to a blog post I wrote sharing more about the how/why if you're interested. I'm a product manager by day, so it's been fun to do some real coding again.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
